Temporally Compressed 3D Gaussian Splatting for Dynamic Scenes

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Javed, Saqib, Khan, Ahmad Jarrar, Dumery, Corentin, Zhao, Chen, Salzmann, Mathieu
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866918216736964608
author Javed, Saqib
Khan, Ahmad Jarrar
Dumery, Corentin
Zhao, Chen
Salzmann, Mathieu
author_facet Javed, Saqib
Khan, Ahmad Jarrar
Dumery, Corentin
Zhao, Chen
Salzmann, Mathieu
contents Recent advancements in high-fidelity dynamic scene reconstruction have leveraged dynamic 3D Gaussians and 4D Gaussian Splatting for realistic scene representation. However, to make these methods viable for real-time applications such as AR/VR, gaming, and rendering on low-power devices, substantial reductions in memory usage and improvements in rendering efficiency are required. While many state-of-the-art methods prioritize lightweight implementations, they struggle in handling {scenes with complex motions or long sequences}. In this work, we introduce Temporally Compressed 3D Gaussian Splatting (TC3DGS), a novel technique designed specifically to effectively compress dynamic 3D Gaussian representations. TC3DGS selectively prunes Gaussians based on their temporal relevance and employs gradient-aware mixed-precision quantization to dynamically compress Gaussian parameters. In addition, TC3DGS exploits an adapted version of the Ramer-Douglas-Peucker algorithm to further reduce storage by interpolating Gaussian trajectories across frames. Our experiments on multiple datasets demonstrate that TC3DGS achieves up to 67$\times$ compression with minimal or no degradation in visual quality. More results and videos are provided in the supplementary. Project Page: https://ahmad-jarrar.github.io/tc-3dgs/
format Preprint
id arxiv_https___arxiv_org_abs_2412_05700
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Temporally Compressed 3D Gaussian Splatting for Dynamic Scenes
Javed, Saqib
Khan, Ahmad Jarrar
Dumery, Corentin
Zhao, Chen
Salzmann, Mathieu
Computer Vision and Pattern Recognition
Graphics
Recent advancements in high-fidelity dynamic scene reconstruction have leveraged dynamic 3D Gaussians and 4D Gaussian Splatting for realistic scene representation. However, to make these methods viable for real-time applications such as AR/VR, gaming, and rendering on low-power devices, substantial reductions in memory usage and improvements in rendering efficiency are required. While many state-of-the-art methods prioritize lightweight implementations, they struggle in handling {scenes with complex motions or long sequences}. In this work, we introduce Temporally Compressed 3D Gaussian Splatting (TC3DGS), a novel technique designed specifically to effectively compress dynamic 3D Gaussian representations. TC3DGS selectively prunes Gaussians based on their temporal relevance and employs gradient-aware mixed-precision quantization to dynamically compress Gaussian parameters. In addition, TC3DGS exploits an adapted version of the Ramer-Douglas-Peucker algorithm to further reduce storage by interpolating Gaussian trajectories across frames. Our experiments on multiple datasets demonstrate that TC3DGS achieves up to 67$\times$ compression with minimal or no degradation in visual quality. More results and videos are provided in the supplementary. Project Page: https://ahmad-jarrar.github.io/tc-3dgs/
title Temporally Compressed 3D Gaussian Splatting for Dynamic Scenes
topic Computer Vision and Pattern Recognition
Graphics
url https://arxiv.org/abs/2412.05700